arXiv:2609.24308v1 Announce Type: new Abstract: Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, int...
Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWor...
The paper introduces TRACE, a cognition-oriented framework that models affective episodes as a sequence of Condition, Affect, and Effect stages, incorporating observable cues and cognitive factors like appraisal and regulation. TRACE-Bench evaluates multimodal models on five tasks—grounded affect recognition, regulation decoding, cause reasoning, effect reasoning, and full-chain reconstruction—using 3,746 question-answer pairs from 646 videos. The authors also present TRACER, a structured reasoning method that links each inference to explicit premises, achieving superior performance across all tasks compared to existing baselines.
arXiv:2607. 00296v1 Announce Type: cross Abstract: Human motion forecasting in unconstrained real-world videos remains challenging due to the ambiguity of future behaviors and the presence of noisy multimodal observations.
arXiv:2609.36776v1 Announce Type: new Abstract: Emotional Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the import...
arXiv:2606. 15032v1 Announce Type: new Abstract: World models have rapidly become one of the central abstractions in modern AI.
arXiv:2609.39147v1 Announce Type: new Abstract: Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are drive...
WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.
arXiv:2609.36563v1 Announce Type: new Abstract: Visual emotion recognition commonly assumes that all evidence required for prediction is contained in the observed image or video. Yet the same visible...
Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven by belief, desire, and perception, requiring in...
OneWorld introduces a shared‑mechanism counterfactual generation framework that jointly models multiple action‑conditioned futures using a common latent physical mechanism. By inferring distributions over latent mechanisms for each action‑outcome branch and aggregating them into shared‑world evidence, the model enforces consistency across interventions while preserving distinct action outcomes. Experiments in controlled environments demonstrate that OneWorld improves cross‑intervention physical consistency without sacrificing single‑rollout prediction quality.
arXiv:2605.15618v2 Announce Type: replace-cross Abstract: Self-supervised video models are increasingly framed as world models, yet they are still evaluated almost entirely on clean video and reporte...